Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add axiomantic/spellbook --skill writing-plansgit clone --depth 1 https://github.com/axiomantic/spellbookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/axiomantic/spellbook/writing-plans)<a href="https://agentmods.dev/skills/axiomantic/spellbook/writing-plans"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/writing-plans/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/axiomantic/spellbook/writing-plans"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/writing-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 68 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.03711 |
| Opus 5 | $0.00041 | $0.01855 |
| Sonnet 5 | $0.00016 | $0.00742 |
| Haiku 4.5 | $0.00008 | $0.00371 |
Grade A, and why
writing-plans scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Plans
Announce: "Using writing-plans skill to create implementation plan."
Invariant Principles
- Zero-Context Assumption - Engineer reading plan knows nothing about codebase, toolset, or domain
- Atomic Tasks - Each step is one action (2-5 min): write test, run test, implement, verify, commit. This governs STEP granularity WITHIN a work item; the revert test (see Work-Item Granularity, adjacent to Capability Groups) governs WORK-ITEM boundaries — the two do not conflict.
- Complete Specification - Full code, exact paths, expected outputs; never "add validation" or similar
- TDD Flow - RED (failing test) -> GREEN (minimal pass) -> commit; repeat
- Traceable Decisions - Link to design doc so reviewers can trace requirements -> plan -> code
Inputs
| Input | Required | Description |
|---|---|---|
| Design document OR requirements | Yes | Spec defining what to build |
| Codebase access | Yes | Ability to inspect existing patterns |
| Target feature name | Yes | Short identifier for plan filename |
Outputs
| Output | Type | Description |
|---|---|---|
| Implementation plan | File | ~/.local/spellbook/docs/<project>/plans/YYYY-MM-DD-<feature>.md |
| Execution guidance | Inline | Choice of subagent-driven vs parallel session |
Reasoning Schema
<analysis>
- What does design doc specify?
- What files exist? What patterns used?
- What's simplest path to working code?
</analysis>
<reflection>
- Does each task have complete code (not placeholders)?
- Can engineer execute without codebase knowledge?
- Are test assertions specific (not just "works")?
</reflection>
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · -59 lines 8bb4a3438d72
- 5d ago First seen · 392 lines · 81 tokens per session scan A ba4acc9825dc
writing-plans is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 3,711 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
atomic-tdd
Test-first discipline. Auto-triggers on "let's implement X", "add feature Y", "fix bug Z", "write a test for", "implement", "build out", and similar pre-code-change phrases. Iron rule: failing test exists before production code. Skip only for pure docs/config changes with an explicit "skipped because:" note. Explicit…
k-feat
A feature-delivery workflow that clarifies a specification and moves from a failing behavior check to a passing one.
k-implement
A development workflow for implementing an existing specification in slices using TDD, a method where tests are written to guide each change. It does not use a separate Work type.
react-web
React web development with hooks, React Query, Zustand.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.